Execute a secure shell in Claude Desktop using the Model Context Protocol.
A Node.js implementation of the Model Context Protocol (MCP) that provides secure shell command execution capabilities. This server allows AI models to execute shell commands in a controlled environment with built-in security measures. Easily integrates with Claude Desktop for connecting Claude with your shell.
Run npx mcp-shell
.
To add it to Claude Desktop, run npx mcp-shell config
. Or add npx -y mcp-shell
to your config manually.
Start (or restart) Claude Desktop and you should see the MCP tool listed on the landing page.
The server implements several security measures:
Command Blacklisting
Command Validation
The server provides one tool:
Executes a shell command and returns its output.
Input Schema:
{
"type": "object",
"properties": {
"command": { "type": "string" }
}
}
Response:
The following command categories are blocked for security:
The server includes comprehensive error handling:
The server is built using:
To modify the security settings, you can:
BLACKLISTED_COMMANDS
set to adjust blocked commandsvalidateCommand
function to add additional validation rulesCallToolRequestSchema
handlerA specialized Model Context Protocol (MCP) server that enables you to search, read, delete and send emails from your Gmail account, leveraging an AI Agent to help with each operation. Optimized for Systemprompt MCP Voice client.
An MCP server that enables communication with users through Telegram. This server provides a tool to ask questions to users and receive their responses via a Telegram bot.
A simple note-taking MCP server for recording and managing notes with AI models.
Enable AI agents to work reliably - giving them secure access to structured data, tools to take action, and the context needed to make smart decisions.